{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:MSDRLNLHLPN4E74KDL452IR2IL","short_pith_number":"pith:MSDRLNLH","schema_version":"1.0","canonical_sha256":"648715b5675bdbc27f8a1af9dd223a42df9f4941c9edf80db2e8a2ffc02afd81","source":{"kind":"arxiv","id":"2601.17717","version":3},"attestation_state":"computed","paper":{"title":"A Survey on Evaluating Quality and Trustworthiness in LLM-Generated Data","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.AI","authors_text":"Chia-Yuan Chang, Fariha Kabir Torsha, Guanchu Wang, Hoang Anh Duy Le, Kaituo Zhang, Mingzhi Hu, Minh Khai Bui, Na Zou, Ying Lin, Yu-Neng Chuang, Zhen Xiong, Zhimeng Jiang","submitted_at":"2026-01-25T06:40:25Z","abstract_excerpt":"Large Language Models (LLMs) have emerged as powerful tools for generating data across various modalities. By transforming data from a scarce resource into a controllable asset, LLMs mitigate the bottlenecks imposed by the acquisition costs of real-world data for model training, evaluation, and system iteration. However, ensuring the high quality of LLM-generated synthetic data remains a critical challenge. Existing research primarily focuses on generation methodologies, with limited direct attention to the quality of the resulting data. Furthermore, most studies are restricted to single modal"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2601.17717","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-01-25T06:40:25Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"0f46df01253da497ed7bf2b9938b84d557f29cdc0e21f127ff5f2e38d4b09974","abstract_canon_sha256":"45a271ea240dd88c6b2a7e5353c08e2904a264e8be25a6102615037092c41ab2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-11T01:09:27.450942Z","signature_b64":"Qme+JHmS9ds4TxbTk6a6NqGGYJwpSq8VTgbgAt5sa6qkxHlGQu488X4mGNX/pq/GOtE2p5KaLfPp0RRMlSM3Dw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"648715b5675bdbc27f8a1af9dd223a42df9f4941c9edf80db2e8a2ffc02afd81","last_reissued_at":"2026-06-11T01:09:27.450032Z","signature_status":"signed_v1","first_computed_at":"2026-06-11T01:09:27.450032Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Survey on Evaluating Quality and Trustworthiness in LLM-Generated Data","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.AI","authors_text":"Chia-Yuan Chang, Fariha Kabir Torsha, Guanchu Wang, Hoang Anh Duy Le, Kaituo Zhang, Mingzhi Hu, Minh Khai Bui, Na Zou, Ying Lin, Yu-Neng Chuang, Zhen Xiong, Zhimeng Jiang","submitted_at":"2026-01-25T06:40:25Z","abstract_excerpt":"Large Language Models (LLMs) have emerged as powerful tools for generating data across various modalities. By transforming data from a scarce resource into a controllable asset, LLMs mitigate the bottlenecks imposed by the acquisition costs of real-world data for model training, evaluation, and system iteration. However, ensuring the high quality of LLM-generated synthetic data remains a critical challenge. Existing research primarily focuses on generation methodologies, with limited direct attention to the quality of the resulting data. Furthermore, most studies are restricted to single modal"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2601.17717","kind":"arxiv","version":3},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2601.17717/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2601.17717","created_at":"2026-06-11T01:09:27.450177+00:00"},{"alias_kind":"arxiv_version","alias_value":"2601.17717v3","created_at":"2026-06-11T01:09:27.450177+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2601.17717","created_at":"2026-06-11T01:09:27.450177+00:00"},{"alias_kind":"pith_short_12","alias_value":"MSDRLNLHLPN4","created_at":"2026-06-11T01:09:27.450177+00:00"},{"alias_kind":"pith_short_16","alias_value":"MSDRLNLHLPN4E74K","created_at":"2026-06-11T01:09:27.450177+00:00"},{"alias_kind":"pith_short_8","alias_value":"MSDRLNLH","created_at":"2026-06-11T01:09:27.450177+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2605.09518","citing_title":"LLM-Driven Performance-Space Augmentation for Meta-Learning-Based Algorithm Selection","ref_index":6,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/MSDRLNLHLPN4E74KDL452IR2IL","json":"https://pith.science/pith/MSDRLNLHLPN4E74KDL452IR2IL.json","graph_json":"https://pith.science/api/pith-number/MSDRLNLHLPN4E74KDL452IR2IL/graph.json","events_json":"https://pith.science/api/pith-number/MSDRLNLHLPN4E74KDL452IR2IL/events.json","paper":"https://pith.science/paper/MSDRLNLH"},"agent_actions":{"view_html":"https://pith.science/pith/MSDRLNLHLPN4E74KDL452IR2IL","download_json":"https://pith.science/pith/MSDRLNLHLPN4E74KDL452IR2IL.json","view_paper":"https://pith.science/paper/MSDRLNLH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2601.17717&json=true","fetch_graph":"https://pith.science/api/pith-number/MSDRLNLHLPN4E74KDL452IR2IL/graph.json","fetch_events":"https://pith.science/api/pith-number/MSDRLNLHLPN4E74KDL452IR2IL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MSDRLNLHLPN4E74KDL452IR2IL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MSDRLNLHLPN4E74KDL452IR2IL/action/storage_attestation","attest_author":"https://pith.science/pith/MSDRLNLHLPN4E74KDL452IR2IL/action/author_attestation","sign_citation":"https://pith.science/pith/MSDRLNLHLPN4E74KDL452IR2IL/action/citation_signature","submit_replication":"https://pith.science/pith/MSDRLNLHLPN4E74KDL452IR2IL/action/replication_record"}},"created_at":"2026-06-11T01:09:27.450177+00:00","updated_at":"2026-06-11T01:09:27.450177+00:00"}